联合多意图识别与语义槽填充的双向交互模型

doi:10.3778/j.issn.1002-8331.2210-0271

摘要/Abstract

摘要： 意图识别与语义槽填充是口语理解的两个主要任务，两者具有高度相关性，通常进行联合训练。随着口语理解任务的深入，研究发现用户在现实场景中的话语往往含有多个意图。但部分联合模型只能识别用户话语中的单个意图，未能充分建模多个意图和语义槽之间的关联性。考虑到话语中多个意图的信息可以引导语义槽填充，语义槽信息也可以帮助意图更好的识别，模型采用图注意力网络建立意图和语义槽之间的双向交互。具体的，将两个任务双向关联以便模型能够挖掘多个意图与语义槽之间的关系，同时引入两个任务的标签信息使模型能够学习到话语上下文和标签的关系，从而提高意图识别与语义槽填充的准确率，优化口语理解的整体性能。实验表明，模型在MixATIS和MixSNIPS两个多意图数据集上对比其他模型性能得到了显著提升。

关键词: 口语理解, 多意图识别, 语义槽填充, 联合模型

Abstract: Intent detection and slot filling are the two major tasks of spoken language understanding, which are highly correlated and are usually trained jointly. As the spoken language understanding task progresses, it has been found that users’ utterances in real-life scenarios often contain multiple intents. However, some joint models can only detect a single intent in user utterances and fail to adequately model the correlation between multiple intents and slots. Since the information of multiple intents in the utterance can guide the slot filling and the slot information can also help the better detection of intents. The Label Bi-Interaction model uses the graph attention network to establish a two-way interaction between intents and slots. Specifically, Label Bi-Interaction model associates two tasks bidirectionally so that the model can explore the relationship between multiple intents and slots, and introduces the label information of the two tasks to enable the model to learn the relationship between utterance context and labels. This improves the accuracy of intent detection and slot filling and optimizes the overall performance of spoken language understanding. Experiments show that the performance of the model on the MixATIS and MixSNIPS two multi-intent datasets has been significantly improved compared to other models.

Key words: spoken language understanding, multi-intent detection, slot filling, joint model

李实, 孙镇鹏. 联合多意图识别与语义槽填充的双向交互模型[J]. 计算机工程与应用, 2024, 60(5): 130-138.

LI Shi, SUN Zhenpeng. Bidirectional Interaction Model for Joint Multiple Intent Detection and Slot Filling[J]. Computer Engineering and Applications, 2024, 60(5): 130-138.

参考文献

[1] QIN L, XIE T, CHE W, et al. A survey on spoken language understanding: recent advances and new frontiers[C]//International Joint Conference on Artificial Intelligence, 2021.
[2] WELD H, HUANG X, LONG S, et al. A survey of joint intent detection and slot-filling models in natural language understanding[J]. ACM Computing Surveys (CSUR), 2021, 55(8): 1-38.
[3] CHEN Q, ZHUO Z, WANG W. BERT for joint intent classification and slot filling[J]. arXiv:1902.10909,2019.
[4] GANGADHARAIAH R, NARAYANASWAMY B. Joint multiple intent detection and slot labeling for goal-oriented dialog[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019.
[5] CUI L, ZHANG Y. Hierarchically-refined label attention network for sequence labeling[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019.
[6] CHEN J, HUANG H, TIAN S, et al. Feature selection for text classification with Naive Bayes[J]. Expert Systems with Applications, 2009, 36(3): 5432-5435.
[7] HAFFNER P, TUR G, WRIGHT J H. Optimizing SVMs for complex call classification[C]//Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003.
[8] SCHAPIRE R E, SINGER Y. BoosTexter: a boosting-based system for text categorization[J]. Machine Learning, 2004, 39: 135-168.
[9] XU P, SARIKAYA R. Convolutional neural network based triangular CRF for joint intent detection and slot filling[C]//Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, 2013.
[10] LECUN Y, BOTTOU L E O, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[11] RAVURI S, STOLCKE A. Recurrent neural network and LSTM models for lexical utterance classification[C]//Proceedings of the Sixteenth Annual Conference of the International Speech Communication Association, 2015.
[12] HOCHREITER S, SCHMIDHUBER J U R. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[13] XIA C, ZHANG C, YAN X, et al. Zero-shot user intent detection via capsule neural networks[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018.
[14] HINTON G E, KRIZHEVSKY A, WANG S D. Transforming auto-encoders[C]//Proceedings of the International Conference on Artificial Neural Networks, 2011.
[15] SABOUR S, FROSST N, HINTON G E. Dynamic routing between capsules[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017.
[16] RABINER L R. A tutorial on hidden Markov models and selected applications in speech recognition[J]. Proceedings of the IEEE, 1989, 77(2): 257-286.
[17] SUN G, GUAN Y, WANG X, et al. A maximum entropy Markov model for chunking[C]//Proceedings of the International Conference on Machine Learning and Cybernetics, 2005.
[18] PENG F, Mccallum A. Information extraction from research papers using conditional random fields[J]. Information Processing and Management, 2006, 42(4): 963-979.
[19] GERS F A, SCHMIDHUBER J U R, CUMMINS F. Learning to forget: continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.
[20] CHO K, VAN MERRI E NBOER B, BAHDANAU D, et al. On the properties of neural machine translation: encoder-decoder approaches[J]. arXiv:1409.1259,2014.
[21] YAO K, ZWEIG G, HWANG M, et al. Recurrent neural networks for language understanding[C]//Proceedings of the Interspeech, 2013.
[22] YAO K, PENG B, ZHANG Y, et al. Spoken language understanding using long short-term memory neural networks[C]//IEEE Spoken Language Technology Workshop (SLT), 2014.
[23] MESNIL G E G, HE X, DENG L, et al. Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding[C]//Proceedings of the Interspeech, 2013.
[24] LIU B, LANE I. Recurrent neural network structured output prediction for spoken language understanding[C]//Proceedings of the NIPS Workshop on Machine Learning for Spoken Language Understanding and Interactions, 2015.
[25] KURATA G, XIANG B, ZHOU B, et al. Leveraging sentence-level information with encoder LSTM for semantic slot filling[J]. arXiv:1601.01530,2016.
[26] HUANG Z, XU W, YU K. Bidirectional LSTM-CRF models for sequence tagging[J]. arXiv:1508.01991,2015.
[27] MA X, HOVY E. End-to-end sequence labeling via bi-directional LSTM-CNNS-CRF[J]. arXiv:1603.01354,2016.
[28] LAMPLE G, BALLESTEROS M, SUBRAMANIAN S, et al. Neural architectures for named entity recognition[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016.
[29] HAKKANI-TüR D Z, G?KHAN T, WANG Y Y, et al. Multi-domain joint semantic frame parsing using bi-directional RNN-LSTM[C]//Proceedings of the 17th Annual Meeting of the International Speech Communication Association, 2016.
[30] ZHANG X, WANG H. A joint model of intent determination and slot filling for spoken language understanding[C]//Proceedings of the International Joint Conference on Artificial Intelligence, 2016.
[31] LIU B, LANE I. Attention-based recurrent neural network models for joint intent detection and slot filling[C]//Proceedings of the Interspeech, 2016: 685-689.
[32] GOO C, GAO G, HSU Y, et al. Slot-gated modeling for joint slot filling and intent prediction[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018.
[33] QIN L, CHE W, LI Y, et al. A stack-propagation framework with token-level intent detection for spoken language understanding[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019.
[34] XU P, SARIKAYA R. Exploiting shared information for multi-intent natural language sentence classification[C]//Proceedings of the Interspeech, 2013.
[35] KIM B, RYU S, LEE G G. Two-stage multi-intent detection for spoken language understanding[J]. Multimedia Tools and Applications, 2017, 76(9): 11377-11390.
[36] 杨春妮, 冯朝胜. 结合句法特征和卷积神经网络的多意图识别模型[J]. 计算机应用, 2018, 38(7): 1839-1845.
YANG C N, FENG C S. Multi-intention recognition model with combination of syntactic feature and convolution neural network[J]. Journal of Computer Applications, 2018, 38(7): 1839-1845.
[37] 刘娇, 李艳玲, 林民. 胶囊网络用于短文本多意图识别的研究[J]. 计算机科学与探索, 2020, 14(10): 1735-1743.
LIU J, LI Y L, LIN M. Research of short text multi-intent detection with capsule network[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(10): 1735-1743.
[38] WANG Y, SHEN Y, JIN H. A bi-model based RNN semantic frame parsing model for intent detection and slot filling[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018.
[39] E H H, NIU P, CHEN Z, et al. A novel bi-directional interrelated model for joint intent detection and slot filling[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019.
[40] QIN L, XU X, CHE W, et al. AGIF: an adaptive graph-interactive framework for joint multiple intent detection and slot filling[C]//Findings of the Association for Computational Linguistics: EMNLP 2020, 2020.
[41] QIN L, WEI F, XIE T, et al. GL-GIN: fast and accurate non-autoregressive model for joint multiple intent detection and slot filling[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021.
[42] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]//Proceedings of the International Conference on Learning Representations, 2018.
[43] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017.